A5054970239- Radiomics and Machine Learning in Medical Imaging
- Head and Neck Cancer Studies
- MRI in cancer diagnosis
- Head and Neck Surgical Oncology
- Pain Mechanisms and Treatments
- Neuroinflammation and Neurodegeneration Mechanisms
- Advanced Neuroimaging Techniques and Applications
- Nanocomposite Films for Food Packaging
- Salivary Gland Tumors Diagnosis and Treatment
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Cerebral Venous Sinus Thrombosis
- Studies on Chitinases and Chitosanases
- Pharmacological Effects of Natural Compounds
- Colorectal and Anal Carcinomas
- Barrier Structure and Function Studies
- Pancreatic and Hepatic Oncology Research
- Musculoskeletal pain and rehabilitation
- Enzyme Production and Characterization
- Ion channel regulation and function
- Alzheimer's disease research and treatments
- Bone Tumor Diagnosis and Treatments
- AI in cancer detection
Fudan University
2018-2025
Eye & ENT Hospital of Fudan University
2021-2024
Shandong University of Science and Technology
2021
State Key Laboratory of Medical Neurobiology
2018-2019
Zhongshan Hospital
2019
Shanghai Ninth People's Hospital
2018-2019
Shanghai Jiao Tong University
2018-2019
This study aimed to assess the diagnostic accuracy of combining MRI hand-crafted (HC) radiomics features with deep transfer learning (DTL) in identifying sinonasal squamous cell carcinoma (SCC), adenoid cystic (ACC), and non-Hodgkin's lymphoma (NHL) using various machine (ML) models. A retrospective analysis 132 patients (50 SCC, 42 NHL, 40 ACC) was conducted. The dataset split 80/20 into training testing cohorts. HC DTL were extracted from T2-weighted, ADC, contrast-enhanced T1-weighted...
Blood-brain barrier (BBB) defects and cerebrovascular dysfunction contribute to amyloid-β (Aβ) brain accumulation drive Alzheimer disease (AD) pathology. By regulating vascular functions inflammation in the microvasculature, a disintegrin metalloprotease with thrombospondin type I motif, member 13 (ADAMTS13) plays significant protective effect atherosclerosis stroke. However, whether ADAMTS13 influences AD pathogenesis remains unclear. Using vivo multiphoton microscopy, histological,...
Purpose Based on comparison of different machine learning (ML) models, we developed the model that integrates traditional hand-crafted (HC) features and ResNet50 network-based deep transfer (DTL) from multiparametric MRI to predict Ki-67 status in sinonasal squamous cell carcinoma (SNSCC). Methods Two hundred thirty-one SNSCC patients were retrospectively reviewed [training cohort (n = 185), test 46)]. Pathological grade, clinical, characteristics analyzed choose independent predictor. HC...
Background The combined prognostic value of texture analysis on computed tomography (CT) and conventional magnetic resonance imaging (MRI) in oral oropharyngeal squamous cell carcinoma (OOSCC) has rarely been reported. Purpose To evaluate the ability texture-based heterogeneity indices extracted from CT MRI to predict overall survival (OS) OOSCC patients. Material Methods Eighty-eight patients with underwent contrast-enhanced CT, T2-weighted (T2W) T1-weighted (T1W) imaging. For each...
Background Memantine is one of the important clinical medications in treating moderate to severe Alzheimer disease. The effect memantine on preventing or punctate allodynia has been thoroughly studied but not induction dynamic allodynia. aim this study investigate whether could prevent and its underlying spinal mechanisms. Results (1) In vivo spared nerve injury pain model, pretreatment with at a lower dose (10 nmol, intrathecal; memantine-10) selectively prevented (2) Pretreatment either...
To develop and validate a nomogram model combining radiomic features clinical characteristics to preoperatively predict the risk of early relapse (ER) in advanced sinonasal squamous cell carcinomas (SNSCCs).A total 152 SNSCC patients (clinical stage III-IV) who underwent diffusion-weighted imaging (DWI) were included this study. The training cohort 106 assessed at headquarters our hospital using MR scanner 1. testing 46 branch 2. Least absolute shrinkage selection operator (LASSO) regression...
A two-dimensional turbo gradient-echo and spin-echo diffusion-weighted pulse sequence with a non-Cartesian BLADE trajectory (TGSE BLADE) can eliminate image artifacts distortion clinically acceptable scan times. This process has the potential to overcome shortcomings of current imaging (DWI) techniques, especially in sinonasal region.To investigate feasibility TGSE assessment lesions compare quality RESOLVE images both qualitatively quantitatively.A total 36 patients were included this...
(1) Background: Chitooligosaccharides (COS) have numerous applications due to their excellent properties. Chitosan hydrolysis using chitosanases has been proposed as an advisable method for COS preparation. Although many from various sources identified, the cold-adapted ones with high stability are still rather rare but required. (2) Methods: A novel chitosanase named CsnY marine bacterium
Objective To explore the value of texture analysis on ADC maps in preoperative prediction histological grade tongue and mouth floor squamous cell carcinoma (SCC). Methods Forty-nine pathologically confirmed SCC with definite grading from May 2015 to June 2018 were retrospectively analyzed, including 21 cases Ⅰ, Ⅱ 7 Ⅲ. All subjects underwent MRI examination DWI included. Two doctors delineated whole tumor region interest extracted parameters by 3D Slicer software, 8 histogram...
Abstract Background The assessment of histologic grade plays an important part in prognosis evaluation squamous cell carcinoma (SCC) the tongue and mouth floor (MF). This study was performed to ascertain if apparent diffusion coefficient (ADC)-based radiomics can predict SCC MF. Methods involved 95 patients (training cohort: n = 63; testing 32), who were categorized as low- high-grade SCCs according pathologic findings. A total 526 features extracted from ADC maps. Radiomics signature...